# HG changeset patch # User elixir-it # Date 1541761592 18000 # Node ID eaac11a49bd23e95469b67c6511217d66a9d9f82 Uploaded diff -r 000000000000 -r eaac11a49bd2 bed_macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bed_macros.xml Fri Nov 09 06:06:32 2018 -0500 @@ -0,0 +1,22 @@ + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r eaac11a49bd2 covacs_varscan2.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/covacs_varscan2.xml Fri Nov 09 06:06:32 2018 -0500 @@ -0,0 +1,167 @@ + + varscan2 wrapper for covacs + + varscan + + + bed_macros.xml + + + + + + + &1 | head -n 1 + ]]> + + samples_list.txt && + #end if + + ## Set up command + input. + varscan ${cmd} ${input} + --min-coverage ${min_coverage} + --min-reads2 ${min_supporting_reads} + --min-avg-qual ${min_avg_qual} + --min-var-freq ${min_var_freq} + --min-freq-for-hom ${min_freq_for_hom} + --p-value ${p_value} + #if str($strand_filter) == 'yes': + --strand-filter 1 + #end if + + ## Report only variants in consensus. + #if str($cmd) == 'mpileup2cns': + --variants + #end if + + ## varscan bed limit added + + #if $bed_source.bed_source_selector == "history" and $bed_source.bed_history + limit $bed_source.bed_history + #end if + #if $bed_source.bed_source_selector == "cached" + limit $bed_source.bed_cached.fields.path + #end if + + ## Set up outputs. + --output-vcf 1 > $output + + #if $sample_names.strip() != '': + --vcf-sample-list samples_list.txt + #end if + + && perl $__tool_directory__/filter.varscan.pl $output $output_filtered + ]]> + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +**VarScan Overview** + +VarScan_ performs variant detection for massively parallel sequencing data, such as exome, WGS, and transcriptome data. It calls variants from a mpileup dataset and produces a VCF 4.1 Full documentation is available online_. + +.. _VarScan: http://dkoboldt.github.io/varscan/ +.. _online: http://dkoboldt.github.io/varscan/using-varscan.html + +**Input** + +:: + + mpileup file - The SAMtools mpileup file + +**the wrapper gives 2 output** + +-the normal output of varscan2 + +-the output filtered by the filter.varscan.pl script implemented in the covacs pipeline + + + +**Parameters** + +:: + + analysis type + single nucleotide detection Identify SNPs from an mpileup file + insertions and deletion Identify indels an mpileup file + consensus genotype Call consensus and variants from an mpileup file + + min-coverage + Minimum read depth at a position to make a call [8] + + min-reads2 + Minimum supporting reads at a position to call variants [2] + + min-avg-qual + Minimum base quality at a position to count a read [15] + + min-var-freq + Minimum variant allele frequency threshold [0.01] + + min-freq-for-hom + Minimum frequency to call homozygote [0.75] + + p-value + Default p-value threshold for calling variants [99e-02] + + strand-filter + Ignore variants with >90% support on one strand [1] + + output-vcf + If set to 1, outputs in VCF format + + vcf-sample-list + For VCF output, a list of sample names in order, one per line + + variants + Report only variant (SNP/indel) positions [0] + + + + 10.1101/gr.129684.111 + 10.1186/s12864-018-4508-1 + + diff -r 000000000000 -r eaac11a49bd2 filter.varscan.pl --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/filter.varscan.pl Fri Nov 09 06:06:32 2018 -0500 @@ -0,0 +1,22 @@ +#!/usr/bin/perl -w +$f=shift; +$outfile=shift; +open(OUT,">$outfile"); +open(IN,$f); +$head=; +print OUT $head; +while() +{ + if ($_=~/^\#/) + { + print OUT; + next; + } + $v=(split())[-1]; + @vl=(split(/\:/,$v)); + $vt=$vl[2]; + if ($vt>=10) + { + print OUT; + } +} diff -r 000000000000 -r eaac11a49bd2 tool-data/covacs_bed.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/covacs_bed.loc.sample Fri Nov 09 06:06:32 2018 -0500 @@ -0,0 +1,17 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory bed file for covacs sequences data files. You will need +#to create these data files and then create a bed_loc.loc file +#similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The bed_loc.loc +#file has this format (longer white space characters are TAB characters): +# +# +# +# +#Note that for backwards compatibility with workflows, the unique ID of +#an entry must be the path that was in the original loc file, because that +#is the value stored in the workflow for that parameter. That is why the +#hg19 entry above looks odd. New genomes can be better-looking. +# +hg19 hg19 hg19-padded /export/BED/S07084713_Padded.bed +hgbed hg19 hg19-bed-test /export/BED/chr22.bed diff -r 000000000000 -r eaac11a49bd2 tool-data/covacs_gatk_indexes.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/covacs_gatk_indexes.loc.sample Fri Nov 09 06:06:32 2018 -0500 @@ -0,0 +1,36 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of all covacs wrapper that need a gatk reference. You will need +#to create these data files and then create a covacs_gatk_indexes.loc file +#similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The covacs_gatk_indexes.loc +#file has this format (longer white space characters are TAB characters): +# +# +# +#So, for example, if you had phiX indexed stored in +#/depot/data2/galaxy/phiX/base/, +#then the bwa_index.loc entry would look like this: +# +#phiX174 phiX phiX Pretty /depot/data2/galaxy/phiX/base/phiX.fa +# +#and your /depot/data2/galaxy/phiX/base/ directory +#would contain phiX.dict, phiX.fa.fai files. +# +# +#Your covacs_gatk_indexes.loc file should include an entry per line for each +#index set you have stored. The "file" in the path does not actually +#exist, but it is the prefix for the actual index files. For example: +# +#phiX174 phiX phiX174 /depot/data2/galaxy/phiX/base/phiX.fa +#hg18canon hg18 hg18 Canonical /depot/data2/galaxy/hg18/base/hg18canon.fa +#hg18full hg18 hg18 Full /depot/data2/galaxy/hg18/base/hg18full.fa +#/orig/path/hg19.fa hg19 hg19 /depot/data2/galaxy/hg19/base/hg19.fa +#...etc... +# +#Note that for backwards compatibility with workflows, the unique ID of +#an entry must be the path that was in the original loc file, because that +#is the value stored in the workflow for that parameter. That is why the +#hg19 entry above looks odd. New genomes can be better-looking. +# +hg38 hg38 hg38_GDC /export/gatkhg38pl/GRCh38.d1.vd1.fa +hg19 hg19 hg19 /export/gatk_hg19_index_bundle/ucsc.hg19.fasta diff -r 000000000000 -r eaac11a49bd2 tool_data_table_conf.xml.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Fri Nov 09 06:06:32 2018 -0500 @@ -0,0 +1,12 @@ + + + + value, dbkey, name, path + +
+ + + value, dbkey, name, path + +
+